Crack width measuring method and system

Abstract

The invention relates to the technical field of crack detection, in particular to a crack width measuring method and system, and the method comprises the following steps: installing information monitoring equipment in a crack to-be-detected area, and obtaining crack detection initial data through the information monitoring equipment; constructing a detection data optimization model, and obtaining crack detection optimization data through the detection data optimization model; establishing a detection data evaluation model, and obtaining crack detection target data based on the detection data evaluation model and the crack detection optimization data; extracting crack detection position information according to the crack detection target data; and measuring the width of the crack to be measured according to a crack width analysis model and the crack detection position information. According to the method, the data optimization, evaluation and measurement model is constructed based on the crack image data, the crack position information can be rapidly extracted, and the crack width can be accurately measured.

Description

Technical Field

[0001] The present invention relates to the technical field of crack detection, and in particular to a crack width measurement method and system. Background Art

[0002] With the rapid development of technologies such as computer vision, image processing, pattern recognition, artificial intelligence, and digital signal processing, the application scenarios of video surveillance technology are becoming increasingly diverse. Intelligent video surveillance technology is particularly regarded as the future development direction of the industry. Existing crack detection technologies and instruments cannot meet the comprehensiveness and accuracy required for practical applications, especially in areas such as optimizing monitoring data or measuring and tracking cracks under various external interference conditions.

[0003] Currently, crack analysis mainly relies on intelligent monitoring instruments and manual recording of information, but the above methods have obvious deficiencies in objectivity, accuracy and authority. In addition, traditional crack detection methods are not thorough enough in data processing, and the detection work is heavy, inaccurate and inefficient.

[0004] Therefore, it is necessary to optimize the existing crack width detection method to achieve efficient search, precise collection, accurate measurement and in-depth analysis of crack measurement data, and further track the changing trend of cracks over a certain period of time, improve the efficiency and accuracy of crack detection, and provide more reliable and accurate data support for related industries. Summary of the Invention

[0005] In response to the shortcomings of existing methods and the needs of practical applications, the present invention uses a dynamic camera to collect data on the crack area to be tested, and uses a data optimization model and an evaluation model to enhance the accuracy of the detection data, so as to better realize the measurement function of the target crack in a complex and dynamic environment, thereby realizing the accurate measurement and objective analysis of the crack width. On the one hand, the present invention provides a crack width measurement method, which includes the following steps: installing an information monitoring device in the crack area to be tested, and using the information monitoring device to obtain initial crack detection data; constructing a detection data optimization model, and obtaining crack detection optimization data through the detection data optimization model; establishing a detection data evaluation model, and obtaining crack detection target data based on the detection data evaluation model and the crack detection optimization data; extracting crack detection position information based on the crack detection target data; and measuring the width of the crack to be tested based on the crack width analysis model and the crack detection position information. Based on the crack detection target data, the present invention accurately extracts the position information of the crack, which helps to accurately analyze the crack situation and is of great significance for assessing the severity of the crack, formulating repair plans, and predicting the development trend of the crack.

[0006] Optionally, installing information monitoring equipment in the crack detection area and obtaining initial crack detection data using the information monitoring equipment includes installing information monitoring equipment in the crack detection area, wherein the information monitoring equipment includes multiple dynamic cameras. The cameras of the present invention can capture crack changes and related data in real time, thereby facilitating understanding of crack changes over different time periods and enabling more accurate determination of the nature and severity of the cracks.

[0007] Optionally, constructing a detection data optimization model and obtaining optimized crack detection data using the detection data optimization model includes: obtaining pixel ratios of the image to be detected based on the initial crack detection data; establishing a detection data optimization model based on the pixel ratios; and obtaining optimized crack detection data using the detection data optimization model. The present invention constructs a detection data optimization model and obtains pre-optimized crack detection data using the model, which can significantly improve data quality, enhance crack feature extraction, reduce computational complexity, improve model generalization capabilities, and provide a solid foundation for subsequent analysis.

[0008] Optionally, the detection data optimization model satisfies the following relationship: in, Represents the optimized image. Represents the minimum output value of the converted image, Represents the grayscale pixel ratio value of the image to be detected, The detection data optimization model of the present invention can be adjusted and optimized according to different situations, thereby better extracting crack features, eliminating interference factors, controlling the output range, improving the degree of automation and computational efficiency, and helping to improve the accuracy and efficiency of crack detection methods.

[0009] Optionally, establishing a detection data evaluation model and obtaining crack detection target data based on the detection data evaluation model and the crack detection optimization data includes: constructing a detection data evaluation model using the crack detection optimization data; and obtaining a data evaluation result of the image to be detected using the detection data evaluation model. The crack detection target data obtained based on the data evaluation model in the present invention can be made closer to reality, reducing the possibility of false detections and missed detections, thereby ensuring the pertinence and effectiveness of the measurement work.

[0010] Optionally, the detection data evaluation model satisfies the following relationship: in, represents the evaluation result of the image data set to be detected, Indicates the total number of images to be detected, Represents the initial data set of the image to be detected, represents the dataset of detection image references, represents the fluctuation coefficient of the data acquisition device, Indicates the external influence weight of the monitored object.

[0011] The present invention comprehensively considers multiple factors to comprehensively evaluate data quality, accurately reflect actual conditions, optimize data processing procedures, provide decision support, and enhance the versatility and adaptability of the model.

[0012] Optionally, obtaining crack detection target data based on the detection data evaluation model and the crack detection optimization data includes: evaluating and analyzing the crack detection optimization data using the detection data evaluation model to obtain a data evaluation result; and combining the data evaluation result with the detection data optimization model to obtain the crack detection target data. The present invention utilizes the combined application of the evaluation model and the optimization model to more accurately reflect the actual conditions and attribute characteristics of cracks, thereby reducing the possibility of false detection and missed detection and improving the accuracy of crack detection results.

[0013] Optionally, extracting crack detection location information based on the crack detection target data includes: constructing a crack location correction model; and obtaining the to-be-detected crack location information based on the crack location correction model and the crack detection target data. Constructing a crack location correction model and extracting crack detection location information based on the model and the crack detection target data can improve the accuracy of location information, optimize data processing procedures, enhance system robustness, and provide reliable support for measurement work.

[0014] Optionally, the measuring the width of the crack to be detected based on the crack width analysis model and the crack detection position information includes: constructing a crack width analysis model; the crack width analysis model satisfies the following relationship: in, Represents the distance between any two detection points in the image to be detected, Indicates the first dimension in the horizontal direction of the first detection point of the image to be detected, Represents the first dimension in the horizontal direction of the second detection point of the image to be detected, Represents the second dimension in the horizontal direction of the first detection point of the image to be detected, Indicates the second dimension in the horizontal direction of the second detection point of the image to be detected, Indicates the third dimension of the first detection point of the image to be detected perpendicular to the horizontal direction of the image, The third dimension of the second detection point of the image to be detected is perpendicular to the horizontal direction of the image. The present invention calculates the distance between any two points in the target image based on the model, and more accurately determines the width of the crack, thereby more comprehensively reflecting the actual width of the crack.

[0015] In a second aspect, to efficiently implement the crack width measurement method provided by the present invention, the present invention further provides a crack width measurement system comprising a processor, an input device, an output device, and a memory, wherein the processor, input device, output device, and memory are interconnected, wherein the memory is used to store a computer program, wherein the computer program includes program instructions, and the processor is configured to invoke the program instructions to execute the crack width measurement method described in the first aspect of the present invention. The crack width measurement system of the present invention has a compact structure and stable performance, and can stably implement the crack width measurement method provided by the present invention, thereby enhancing the overall applicability and practical application capabilities of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 This is a flow chart of the crack width measurement method of the present invention; Figure 2 A schematic diagram of a deformity variation detection device for a crack width measurement method according to the present invention; Figure 3 This is a flow chart of crack position information extraction in the crack width measurement method of the present invention; Figure 4 Schematic diagram showing the comparison of data errors of different crack width measurement methods of the present invention; Figure 5 This is a structural diagram of the crack width measurement system of the present invention. DETAILED DESCRIPTION

[0017] Specific embodiments of the present invention will be described in detail below. It should be noted that the embodiments described herein are for illustrative purposes only and are not intended to limit the present invention. In the following description, numerous specific details are set forth to provide a thorough understanding of the present invention. However, it will be apparent to one of ordinary skill in the art that these specific details are not necessarily required to practice the present invention. In other instances, well-known circuits, software, or methods are not specifically described to avoid obscuring the present invention.

[0018] Throughout this specification, references to "one embodiment," "an embodiment," "an example," or "an example" mean that a particular feature, structure, or characteristic described in connection with the embodiment or example is included in at least one embodiment of the present invention. Therefore, appearances of the phrases "in one embodiment," "in an embodiment," "an example," or "an example" in various places throughout this specification are not necessarily all referring to the same embodiment or example. Furthermore, the particular features, structures, or characteristics may be combined in any suitable combinations and / or subcombinations in one or more embodiments or examples. Furthermore, those of ordinary skill in the art will appreciate that the figures provided herein are for illustrative purposes only and are not necessarily drawn to scale.

[0019] See Figure 1 , using a camera to collect image data of the crack area to be tested in real time, and using a data optimization model and an evaluation model to finely process and evaluate the collected data, significantly improving the accuracy of the detection data, thereby enabling efficient and accurate measurement of the target crack and ensuring the reliability of the crack width measurement results. The present invention provides a crack width measurement method, which includes the following steps: S1. Set up information monitoring equipment in the crack detection area and use the information monitoring equipment to obtain initial crack detection data. The specific implementation steps and contents are as follows; The information monitoring equipment is set according to the crack detection area. In the embodiment, the information monitoring equipment includes multiple dynamic cameras. The specific implementation content is as follows: First, analyze the crack area to be tested, including but not limited to its shape, area, terrain, and activity patterns. Based on these characteristics and actual needs, select the appropriate dynamic camera model. Because different cameras vary in performance and functionality, key parameters such as the number of cameras, deployment locations, and device frame rate must be tailored to the specific conditions of the test area.

[0020] When selecting a camera model, carefully configure and adjust the various parameters of the camera based on the actual situation of the area to be tested and the data detection requirements. The above parameters include but are not limited to frame rate, resolution, color performance, brightness, contrast, and storage space to ensure that the captured crack detection images have excellent quality and clarity.

[0021] In addition, factors such as the angle, range, and height of crack detection will be comprehensively considered, and the dynamic positions of multiple cameras will be carefully selected and designed to ensure that the coverage and clarity of the detection equipment are optimal, while ensuring that each camera can accurately capture the key parts of the crack. When deploying the camera, special attention will be paid to its monitoring height and angle, and blind spots in data collection will be avoided as much as possible to ensure that the best detection images of the cracks to be measured can be obtained, further realizing comprehensive, efficient, and accurate monitoring of the crack area to be tested, and providing a solid foundation for subsequent data analysis and processing.

[0022] Next, multiple cameras will be connected via signal cables to ensure stable communication with the data storage device. Each camera will then be debugged with the data storage system to ensure accurate transmission of test data to the device. During the debugging process, key camera parameters such as focal length, aperture, and color will be adjusted to optimize image clarity and improve data accuracy. Furthermore, to ensure the integrity and traceability of monitoring data, a data storage solution is designed into the data storage device to securely store all test data, facilitating subsequent data storage and query.

[0023] Furthermore, to maintain the normal operation of the data storage device, the detection data is regularly analyzed and processed to promptly identify and resolve any potential problems. This ensures the proper functioning of the entire crack detection method and provides reliable data support for crack width monitoring and analysis.

[0024] Furthermore, the monitoring method and data acquisition method of the camera in this embodiment are only optional conditions of the present invention. In other embodiments, the detection equipment can be flexibly selected according to actual needs. Through the collaborative work of multiple cameras, effective detection of the target to be measured can be achieved, the crack width and changes can be analyzed more accurately, the accuracy of the detection data can be improved, and the practicality and accuracy of the crack width measurement method can be enhanced.

[0025] S2. Construct a detection data optimization model, and obtain crack detection optimization data through the detection data optimization model. The specific implementation steps and contents are as follows; The pixel ratio of the crack image to be detected is analyzed based on the initial crack detection data to explore the proportion of specific grayscale pixels in the detection image, so as to more comprehensively understand the relevant characteristics of the crack image. In the embodiment, the pixel ratio analysis satisfies the following relationship: in, Indicates the ratio of specific grayscale pixels in the image to be detected. Indicates the stability factor of the detection equipment, Indicates the number of image pixels that meet a specific range of grayscale values. Indicates the total number of pixels in the image to be detected.

[0026] The specific grayscale pixel ratio value in an image refers to the proportion or ratio of grayscale values ​​within a specific range in the crack detection image. A grayscale image is an image that contains only brightness information and not color information. Its pixel values ​​typically range from black to white, representing different brightness levels. In this embodiment, the grayscale pixel ratio value is derived from the ratio of the number of specific pixels in the image to the total number of pixels in the image. It reflects the proportion of specific grayscale pixels in the image, further understanding the brightness distribution, contrast, and noise of the crack detection image.

[0027] The stability factor of a crack detection device is an important indicator of its ability to maintain its posture or operational stability under specific environmental conditions. It reflects the system's ability to maintain stability and balance when subjected to external forces or environmental changes. A higher stability factor indicates greater stability, ensuring accurate and reliable measurement results under various environmental conditions. Therefore, the stability factor is a key consideration when selecting and using crack detection equipment to ensure the accuracy and reliability of test results.

[0028] In crack detection applications, the number of image pixels that meet a specific range of grayscale values ​​refers to the number of pixels in the grayscale image whose grayscale values ​​fall within a specific range. This specific range is usually determined based on the empirical value of the crack grayscale, aiming to effectively distinguish between cracks and background areas. First, when the grayscale of the crack is significantly different from that of the background, a global threshold method can be used. In an optional embodiment, a maximum grayscale value (max_crack_gray) is set, which represents the maximum grayscale value that the crack is expected to reach. In this method, all pixels in the image with grayscale values ​​less than max_crack_gray are regarded as crack areas, while pixels with grayscale values ​​greater than or equal to max_crack_gray are regarded as background areas. By counting the number of pixels less than max_crack_gray, the number of pixels in the crack area can be obtained.

[0029] When the crack grayscale is close to the background grayscale, a global threshold method is used. In this case, the average grayscale or Gaussian-weighted grayscale of the local neighborhood of each pixel in the image needs to be calculated and compared with a dynamic threshold. This allows for more accurate identification of crack areas based on the characteristics of the pixel neighborhood.

[0030] Furthermore, if more precise control of the distribution of grayscale values ​​is required, a grayscale mapping method can be used. In another optional embodiment, the grayscale values ​​of the original image are mapped to a new grayscale value range to ensure that the grayscale values ​​of the cracks fall within the specified range. By adjusting the mapping function, the contrast between the cracks and the background can be enhanced, making it easier to identify the crack area.

[0031] Based on this, we can determine the number of pixels within a specific grayscale value range in the crack detection grayscale image. This number of pixels provides important information about the size and distribution of the crack area, which helps with subsequent crack analysis and treatment.

[0032] Each pixel in a grayscale image has a grayscale value, which represents the brightness of the corresponding pixel. The brightness range area or feature of the monitoring image can be calculated by the number of pixels in a specific grayscale value range, which helps in subsequent image analysis, processing, and recognition processes.

[0033] The total number of pixels in the image to be inspected refers to the total number of all pixels in the crack detection image. In digital image processing, images are composed of pixels, each of which is the smallest unit of the image, including but not limited to information such as color and brightness. Therefore, the total number of pixels in the image to be inspected is the sum of the pixels that make up the image to be inspected. Furthermore, the number of pixels is related to the image resolution: higher resolution means more pixels and richer image detail. Based on the total number of pixels in the image to be inspected, we can understand the size and complexity of the image, providing basic data for subsequent crack image processing and analysis.

[0034] Then, a detection data optimization model is established based on the pixel ratio of the image to be detected to obtain accurate information of the crack image to be detected. The specific implementation content is as follows: First, the grayscale to be detected needs to be nonlinearly transformed, that is, the grayscale in the crack detection image is nonlinearly mapped or adjusted. The main purpose of image transformation is to expand or compress the grayscale range of the image in order to better display the details of the crack detection image or adapt to specific display requirements.

[0035] In an optional embodiment, when the grayscale display range of the display is limited, directly displaying certain images with a larger grayscale value range may result in loss of some details or insufficient contrast. Therefore, logarithmic transformation and nonlinear operations are performed on the grayscale values ​​to map the originally wider grayscale range to a narrower range, thereby enabling the display to provide better display.

[0036] In the embodiment, the logarithmic transformation needs to satisfy the following relationship: in, Represents the output result of the converted image to be detected, Represents the grayscale scaling factor of the image to be detected, Indicates the ratio of specific grayscale pixels in the image to be detected.

[0037] The converted image output result refers to the image data or representation obtained after the grayscale nonlinear transformation of the image to be detected. During the conversion process, the grayscale value of the original image is adjusted and processed, and the image grayscale is converted through logarithmic transformation, power law transformation or other nonlinear transformation methods.

[0038] The grayscale scaling factor of an image under inspection refers to a proportional factor used to adjust or alter the grayscale value range of an image during image processing. This factor determines the degree to which grayscale values ​​are increased or decreased, thereby adjusting the brightness and contrast of the image under inspection. By using different scaling factors, the grayscale range of an image can be stretched or compressed to optimize the visual effect or adapt to specific processing requirements.

[0039] In the embodiment, the value of the stretch coefficient can be determined based on the original grayscale distribution of the image to be detected, the processing purpose and the expected effect. A larger stretch coefficient usually leads to a larger change in the grayscale value, thereby enhancing the contrast of the image; while a smaller stretch coefficient may produce a more gentle adjustment to the grayscale value, which can maintain the softness and detail information of the image.

[0040] In this embodiment, based on the logarithmic transformation formula and combined with the ratio results of different grayscale pixels in the image to be detected, an in-depth analysis of the output maximum and minimum values ​​of the image to be detected is performed, which helps to more accurately understand the grayscale distribution characteristics of the image and provide strong support for subsequent processing and analysis work.

[0041] The maximum output value of the image after the grayscale nonlinear transformation refers to the maximum brightness value that the image to be detected can reach in the grayscale after the logarithmic transformation. In the embodiment, the maximum output value reflects the performance of the pixel with the highest brightness in the image after logarithmic transformation, which is closely related to the contrast, brightness distribution and transformation parameter settings of the image. Based on the maximum output value, the brightness range and distribution of the image after transformation can be understood, so as to further evaluate the impact of the logarithmic transformation on the image quality and whether it meets specific application requirements. In crack detection applications, changes in the maximum output value reveal the brightness characteristics of the crack area, which helps to more accurately identify and analyze the morphology and distribution of cracks.

[0042] The minimum output value of an image after a grayscale nonlinear transformation refers to the minimum brightness value that the image to be detected can achieve in grayscale after logarithmic transformation. The minimum output value reflects the performance of the lowest-brightness pixel in the image after logarithmic transformation, and is related to the dark details of the image, the noise level, and the setting of the transformation parameters. In the actual application of crack detection, changes in the minimum output value reveal detailed information about the dark areas of the image, including but not limited to the starting point, depth, or width of the crack. By analyzing the minimum output value to compare the dark details retained in the image after transformation, crack features can be more accurately identified and extracted. This also helps to evaluate the contrast of the detected image, highlight crack edges, and other related information.

[0043] Based on the results of the grayscale pixel ratio analysis and nonlinear transformation of the image to be detected, the image to be detected is optimized. In this embodiment, the grayscale value distribution of the pixels in the image to be detected is adjusted to make it closer to a uniform distribution. In an optional embodiment, the originally unevenly distributed image histogram is made approximately uniform, thereby achieving an improvement in image contrast. After the equalization optimization process, the pixels in the image can more fully utilize each grayscale level, making the grayscale distribution more uniform, significantly improving the dynamic range and contrast of the image to be detected, enhancing the image contrast and visual effect, and making the image to be detected more vivid, clear, and accurate.

[0044] In this embodiment, the above detection data optimization model satisfies the following relationship: in, Represents the grayscale pixels of the image to be detected after optimization, Represents the minimum output value of the image to be detected after grayscale nonlinear transformation, Represents the grayscale pixel ratio value of the image to be detected, Indicates the maximum output value of the image to be detected after grayscale nonlinear transformation.

[0045] The detection data optimization model is used to redistribute the pixel values ​​of the image to be detected, so that the dark and bright details of the image can be better displayed, thereby significantly enhancing the contrast of the entire image, making the details of the image to be detected more obvious, and improving the data quality. On the other hand, it helps to improve the quality and readability of the image, thereby improving the accuracy and robustness of the data optimization algorithm.

[0046] Then, the crack detection optimization data is obtained by using the detection data optimization model.

[0047] The detection data optimization model is fully utilized to optimize the initial crack detection data to obtain more accurate crack detection optimization data. In an optional embodiment, the initial crack detection data is first preprocessed, including but not limited to data cleaning, denoising, and standard conversion operations to ensure the accuracy and consistency of the initial data. Subsequently, the above initial data is input into the crack detection model to obtain crack detection optimization data. On the other hand, based on the initial data and optimization results, the detection data optimization model is iteratively trained, model parameters are adjusted, and algorithm optimization is performed to enable it to better identify and process the initial crack data. Ultimately, through the above series of optimization operations, the crack detection pre-optimization data is finally obtained. The above data not only has higher accuracy and reliability, but also can better reflect the actual situation of the cracks, providing strong support for subsequent crack analysis and processing.

[0048] Furthermore, the initial data optimization processing method in this embodiment is only an optional condition of the present invention. In one or some other embodiments, the detection data optimization method can be replaced according to the data collection situation and target requirements to improve the accuracy, reliability and readability of the detection data, while improving the actual performance of the data processing model.

[0049] S3. Establish a test data evaluation model, and obtain crack detection target data based on the test data evaluation model and crack detection pre-optimization data. The specific implementation steps and contents are as follows: A detection data evaluation model is established based on the crack detection optimization data, and the data evaluation results of the images to be detected are analyzed by the detection data evaluation model. The specific implementation content is as follows: Utilizing crack detection optimization data, we further constructed a test data evaluation model. This model comprehensively evaluates and analyzes the optimized data of the images to be inspected, thereby ensuring the accuracy and validity of crack-related data. By applying this model, we can more accurately determine the crack conditions in the images to be inspected, providing a scientific basis for subsequent crack monitoring and measurement, thereby ensuring the accuracy and reliability of crack detection results.

[0050] In this embodiment, the detection data evaluation model satisfies the following relationship: in, represents the evaluation result of the image data set to be detected, Indicates the total number of images to be detected, Represents the initial data set of the image to be detected, represents the dataset of detection image references, represents the fluctuation coefficient of the data acquisition device, Indicates the external influence weight of the monitored object.

[0051] The evaluation results of the image dataset to be tested refer to the comprehensive assessment conclusions drawn after a comprehensive analysis of the dataset using the test data evaluation model. These results primarily cover the crack detection status of the images to be tested in the dataset, including but not limited to the accuracy, completeness, and reliability of information such as the crack location, morphology, and size. Furthermore, the evaluation results comprehensively consider indicators such as the crack recognition rate, false positive rate, and missed detection rate for all images in the dataset, as well as factors such as the clarity, contrast, and noise level of the image data. These indicators and factors are comprehensively analyzed to determine the overall performance of the image dataset in crack detection.

[0052] The total number of images to be inspected refers to the total number of images to be processed, analyzed, or evaluated in this embodiment. These images are typically collected based on specific application requirements and actual circumstances. In actual crack detection scenarios, the number of images may vary depending on various factors, including but not limited to images collected over different time periods, images from different locations or regions, and images of different resolutions or formats.

[0053] The initial image data set refers to the raw image data collected in step S1 before crack detection or other related image processing tasks. This includes, but is not limited to, crack images taken from different angles, distances, and lighting conditions, as well as images of various crack backgrounds and interfering factors. These images have different resolutions, color spaces, and formats, reflecting the specific appearance and information characteristics of the cracks under different conditions.

[0054] The dataset of detection image references refers to the optimal image dataset for crack detection. In embodiments, this dataset is further optimized and organized based on the initial image dataset to meet the specific requirements of crack measurement tasks. In embodiments, the requirements and conditions for the reference image dataset can be set in advance based on the conditions of the crack area to be measured, the initial data status, and the width measurement target, so that the algorithm or model can better optimize the crack data and achieve accurate and efficient crack width detection.

[0055] The coefficient of fluctuation of a data acquisition device is a numerical indicator that indicates the degree of data variation during the device's data collection process. It can be used to assess the relative dispersion of data. A larger coefficient of fluctuation indicates greater data variation, indicating that the data acquisition device may experience significant fluctuations or instability during the collection process. A smaller coefficient of fluctuation indicates less relative dispersion, a relatively stable data distribution, and more stable data acquisition device performance.

[0056] The coefficient of fluctuation can help better understand and evaluate the performance of data acquisition equipment, as well as the accuracy and reliability of data collection results. A high coefficient of fluctuation may indicate the need to review the equipment's operating status, environmental conditions, or data collection methods, and make appropriate optimizations or adjustments. The coefficient of fluctuation can also serve as a risk assessment parameter, helping to predict and avoid potential problems and develop a more reasonable and reliable initial data collection plan.

[0057] The external influence weight of a monitored object specifically refers to the degree or proportion of influence of external factors on the state or performance of the monitored object. During crack measurement, monitored objects, including but not limited to buildings, bridges, and other structures, are subject to a variety of external factors, including but not limited to wind, temperature, humidity, vibration, and load. These factors can cause deformation of the crack structure, stress changes, or degradation of material properties, thereby affecting the initiation, development, and distribution of cracks. Quantifying the external influence weights can reflect the impact of different external factors on cracks, thereby enabling better data collection plans and width measurement methods.

[0058] Then, the detection data evaluation model is used to evaluate and analyze the initial crack detection data, and the data evaluation results are obtained.

[0059] The evaluation model analyzes each image in the crack detection data one by one to obtain the evaluation results of the image data set to be detected. At the same time, the crack features in the images to be detected are extracted and compared with existing standard features. The crack detection data images are further comprehensively evaluated by combining the evaluation results, data feature matching, false detection rate, missed detection rate and other key indicators. The evaluation and analysis of the crack detection data using the detection data evaluation model ensures the accuracy and effectiveness of the crack detection data, laying a solid foundation for subsequent crack detection work.

[0060] Finally, the crack detection target data is obtained by combining the data evaluation results and the detection data optimization model.

[0061] Comparing and analyzing the data evaluation results with existing high-quality data and standard indicator data, and identifying deficiencies and defects in the initial crack detection data through comparison, not only helps to deeply understand the practical performance of crack detection data, but also provides clear guidance for subsequent data optimization.

[0062] Comparative analysis reveals gaps in the initial data, including but not limited to key metrics such as data feature extraction accuracy, false positive rate, and missed detection rate. Based on these comparisons and the detection data optimization model, the crack detection data is iteratively optimized. This iterative optimization process includes but is not limited to adjusting the parameters of the data optimization model, improving feature extraction methods, and optimizing the data processing process, thereby improving the accuracy and reliability of the crack detection data.

[0063] In an optional embodiment, the difference between the dataset evaluation result and the standard reference dataset is analyzed to determine the parameter direction that needs to be adjusted.

[0064] Although the total number of images itself is not a directly adjustable parameter, it will affect the efficiency and accuracy of iterative optimization. More images can provide more data support, helping the algorithm to better learn and adapt to crack characteristics. However, too many images may also increase the computational burden and complexity. Therefore, in practical applications, the total number of images needs to be reasonably selected based on computing resources and time costs.

[0065] The fluctuation coefficient of the data acquisition device can be used to compensate for the impact of device instability on image quality. Data acquisition devices can experience fluctuations due to factors such as device aging, temperature changes, and mechanical vibration. In practical applications, adjusting the fluctuation coefficient based on comparison results can reduce the impact of these fluctuations on crack detection results and improve algorithm accuracy.

[0066] The external influence weight of the monitored object is used to consider the impact of external environmental factors such as light, shadow, and occlusion on crack characteristics. Different application scenarios and environmental conditions require matching different external influence weights. By adjusting the external influence weight, the algorithm can better adapt to different environmental conditions and improve the accuracy and robustness of crack detection.

[0067] During the iterative optimization process, the adjustment of model parameters needs to be comprehensively considered based on specific task requirements, data characteristics, and algorithm performance. Through continuous trial and adjustment, the optimal parameter combination can be found to achieve more accurate crack detection and more efficient image processing.

[0068] In an optional embodiment, the gap between the initial data and the high-quality data or standard indicators can be gradually narrowed through multiple iterative optimizations, and finally the crack detection target data is obtained. The above target data not only has higher accuracy and meets the needs of practical applications, but also can provide solid data support for subsequent crack monitoring and processing.

[0069] In this embodiment, the data evaluation results are compared and analyzed with high-quality data and standard indicator data, and iterative optimization is performed in combination with the detection data optimization model to obtain high-quality crack detection target data. This not only improves the performance of crack detection data, but also provides a reference basis for the continuous optimization of crack detection algorithms and models.

[0070] Furthermore, the method for obtaining crack detection target data in this embodiment is only an optional condition of this embodiment. In one or some other embodiments, the data optimization method can be adjusted according to data requirements. The data optimization method can be adjusted accordingly according to specific data requirements, thereby improving the applicability and flexibility of the crack width measurement method.

[0071] S4. Extract crack detection location information based on crack detection target data. The specific implementation steps and contents are as follows: In the crack detection method, a camera or other type of image acquisition device can be used to establish a coordinate system centered on the camera. The coordinate system can describe the corresponding relationship between the camera and the crack surface to be detected or other detection objects.

[0072] In this embodiment, the image acquisition device, or camera in this embodiment, defines the origin of the camera coordinate system at the optical center of the camera, i.e., the center point of the lens. The X-axis is generally parallel to the horizontal direction of the image sensor, with the positive direction pointing to the right of the image sensor; the Y-axis is parallel to the vertical direction of the image sensor, with the positive direction pointing downward; and the Z-axis is perpendicular to the image sensor plane and points forward of the camera lens, i.e., the direction of capture. Based on this, a correspondence is established with the inspection object. Through the camera coordinate system, it is possible to clearly determine the specific location of each pixel in the image on the crack surface or other inspection object in the real world.

[0073] In the embodiment, establishing a coordinate system centered on the camera is one of the steps in the crack detection method, which helps to accurately describe the correspondence between the camera and the crack surface to be detected or other detection objects, and provides important spatial information for subsequent crack detection and positioning. Due to the lack of precision or process deviations in the manufacturing and assembly process of the detection camera lens, the camera will be distorted, which will cause the captured detection image to be distorted, and thus cannot accurately restore the actual scene. For the deformation variation of the detection equipment, please refer to Figure 2 , where A represents the actual position of the crack to be detected, A1 represents the ideal shooting position of the crack to be detected, A2 represents the radial distortion position of the crack to be detected, and A3 represents the tangential distortion position of the crack to be detected.

[0074] Among them, the tangential distortion of the detection equipment mainly comes from the assembly process of the camera. The lens and the imaging surface cannot be strictly parallel during the assembly process of the detection equipment. Radial distortion is a typical lens distortion phenomenon. Its main feature is that the distortion is distributed along the radius of the lens. This distortion is caused by the refraction of the center part of the light more curved than the edge part when passing through the lens.

[0075] Furthermore, radial distortion can be divided into barrel distortion and pincushion distortion. Barrel distortion is characterized by the image's central region protruding outward, like an inverted barrel; pincushion distortion, on the other hand, is the opposite, with the image's central region concave inward, resembling a pillow. Both forms of distortion are evident in crack detection images.

[0076] In one optional embodiment, when the distortion at the center of the optical axis reaches its minimum value, approaching zero, the distortion becomes increasingly pronounced as the lens radius increases, manifesting as increased image distortion. To reduce the impact of device distortion on crack detection data, adjustment parameters are introduced to optimize the crack's location to restore the actual state of the crack being detected.

[0077] A crack position correction model is constructed based on the crack detection data. The crack image coordinates are adjusted using the model to obtain a crack image closer to the real scene. The image coordinate correction model satisfies the following relationship: in, Represents the first horizontal dimension of the image after correction. Represents the first dimension of the image in the horizontal direction, represents the first adjustment weight, Indicates the lens radius value of the detection device. represents the second adjustment weight, represents the third adjustment weight, Represents the second dimension of the horizontal direction of the image after correction. Represents the second dimension of the image in the horizontal direction, Represents the third dimension perpendicular to the horizontal direction of the image after correction. Represents the third dimension perpendicular to the horizontal direction of the image.

[0078] The calibrated image dimensions refer to the new position coordinates of each pixel in the image after distortion correction. During the calibration process, the crack image coordinates are adjusted based on a mathematical distortion model to eliminate image distortion caused by lens distortion. This repositions pixels that were originally offset due to distortion to their proper positions, resulting in a more accurate, distortion-free image. This provides accurate feedback on the spatial position of the crack image, allowing for a more realistic representation of objects and scenes in the crack detection image, improving the accuracy and reliability of the image processing results.

[0079] Image coordinate adjustment weights refer to the process of assigning different adjustment coefficients or weights to different pixel points or regions during the image coordinate calibration process based on the degree of distortion. Because camera distortion varies at different locations and in different directions, the image coordinate adjustment process requires setting different weights based on the degree of distortion for each pixel point or region to achieve more accurate position correction.

[0080] In an optional embodiment, the image adjustment weight needs to be determined based on factors such as the distortion model of the detection equipment, lens characteristics, and actual shooting conditions. For areas with more severe distortion, a larger adjustment weight value is assigned to facilitate larger coordinate adjustments; conversely, for areas with less distortion, a smaller adjustment weight value is used to avoid over-correction. Reasonable setting of the image adjustment weight can achieve differentiated processing of distortion in different areas of the image, thereby improving the correction effect of the entire detection image, helping to restore the true shape and size of the crack detection image, improving the quality of the detection image, and providing a more accurate data basis for subsequent crack measurements.

[0081] The crack detection location information is extracted based on the crack location correction model and crack detection target data. The specific implementation content is as follows: Crack detection target data is used to extract crack detection location information. In the process of extracting location information, the crack's morphology, length, width and other characteristics must also be considered. These characteristics are crucial for analyzing the stability and safety of cracks. Therefore, it is necessary to use appropriate algorithms and techniques to accurately measure and describe crack-related characteristics. Then, the extracted crack location information is combined with the correction model to further correct and optimize the crack location, thereby obtaining more accurate and reliable crack location information to support subsequent crack width measurement. For the specific process of extracting crack detection location information, please refer to Figure 3 , where (x1, y1) represents the coordinates of the first pixel point of the crack image, (x11, y11) represents the coordinates of the first pixel point of the crack image after dimensional processing, (x1, y1, z1) represents the three-dimensional coordinates of the first pixel point of the crack image, (x2, y2) represents the coordinates of the second pixel point of the crack image, (x21, y21) represents the coordinates of the second pixel point of the crack image after dimensional processing, (x2, y2, z2) represents the three-dimensional coordinates of the second pixel point of the crack image, c1 represents the crack image feature matching program, c2 represents the crack image pixel point coordinate dimensional processing program, c3 represents the crack image pixel point three-dimensional coordinate calculation program, S represents the crack detection position information set, where dimensional processing refers to the optimization processing of the coordinates of each pixel point of the crack image using the image coordinate calibration model.

[0082] Furthermore, the analysis steps and processing methods for the crack position information in this embodiment are only an optional condition of this embodiment. In one or some other embodiments, the method for obtaining the crack position data can be optimized according to the implementation conditions and actual data conditions, which not only improves the adaptability and flexibility of the crack width measurement method, but also improves the data processing efficiency and accuracy.

[0083] S5. Measure the width of the crack to be detected based on the crack width analysis model and the crack detection position information. The specific implementation steps and contents are as follows: In this embodiment, according to the formation mechanism and influencing factors of cracks, appropriate prediction theories and simulation methods are selected to establish a crack width analysis model. Based on the above theories and methods, an analysis model of crack width is established. At the same time, some crack target detection data are randomly selected to train and verify the analysis model. The prediction accuracy and reliability of the analysis model are verified based on the training results to improve the performance of the analysis model.

[0084] The above crack width analysis model satisfies the following relationship: in, Represents the distance between any two detection points in the image to be detected, Indicates the first dimension in the horizontal direction of the first detection point of the image to be detected, Represents the first dimension in the horizontal direction of the second detection point of the image to be detected, Represents the second dimension in the horizontal direction of the first detection point of the image to be detected, Indicates the second dimension in the horizontal direction of the second detection point of the image to be detected, Indicates the third dimension of the first detection point of the image to be detected perpendicular to the horizontal direction of the image, Indicates the third dimension of the second detection point of the image to be detected, which is perpendicular to the horizontal direction of the image.

[0085] In the embodiment, two or more detection points are randomly selected in the image of the crack to be detected, and then the distance value between the detection points is solved based on the above detection points, and the distance of the crack to be detected is analyzed based on the distance between different detection points.

[0086] The distance between any two detection points in the image to be detected refers to the two pixels or feature points of the crack image randomly selected as the detection points in the image to be detected, and the spatial distance between them is calculated. This helps to quickly understand the shape, size and position relationship of the cracks in the image to be detected, and then measure the actual distance value of the cracks.

[0087] Furthermore, based on the calibrated and verified crack location data and the crack width analysis model, the numerical results of the width of the crack to be detected can be accurately obtained. The output results of the above model not only reflect the actual width of the crack, but also provide an important basis for quantitative analysis and evaluation of the crack condition.

[0088] Furthermore, to verify the beneficial effects and practical value of the crack width measurement method of the present invention, a comparative analysis is now conducted between the crack width measurement method proposed in the present invention and the existing measurement methods. The specific implementation contents are as follows: Real-world cracks have diverse inclination angles, making it difficult for detection equipment to capture images perfectly parallel to the crack surface. Therefore, capturing images of the crack under inspection at different angles for measurement becomes essential. Current monocular camera acquisition technology primarily relies on two-dimensional image processing for crack measurement. However, due to variations in camera angle, the calculated crack dimensions often exhibit significant errors.

[0089] To verify the accuracy and reliability of the measurement method of the present invention, this example employed simultaneous multi-device measurement technology, and the results were compared with those from monocular measurement. See Table 1 for details. In this example, two sets of representative images of cracks to be detected were captured using dual cameras, designated Group A and Group B. This comparative analysis of the measurement results from different data acquisition methods more intuitively demonstrates the advantages of the present measurement method in terms of camera angles, providing more accurate and reliable crack size data for practical applications.

[0090] Table 1 Data comparison table of different crack data acquisition methods As shown in Table 1, each set of crack data capture was captured from three different camera angles, allowing for a more comprehensive capture of the crack's morphology and size from different viewing angles. The crack width measurement method of the present invention was then used to measure the width of the crack to be detected, where the width specifically refers to the value at the widest point of the crack in the image.

[0091] In order to verify the beneficial effects of the crack width measurement method, in this embodiment, the field measurement values ​​are used as standard reference values, and the measurement results and error comparison data of the verification crack width measurement method are collated and analyzed. At the same time, in order to more intuitively analyze the differences between the present invention and the existing verification measurement method and to more clearly show the trend of measurement error, the data error results of different measurement methods are plotted as a line graph for display. For details, please refer to Figure 4 .

[0092] The present invention proposes a crack width measurement method and system. Information detection equipment is arranged within a predetermined crack detection area to obtain initial crack detection data. A detection data optimization model is then constructed to optimize the initial data, thereby obtaining more accurate crack detection optimization data. A detection data evaluation model is then established to further extract target data information for crack detection based on the relevant mathematical model and the optimized data. Based on this target data information, the crack location information can be accurately analyzed. Finally, the crack width analysis model and the crack location information are combined to accurately measure the width of the crack to be measured. By constructing data optimization, evaluation, and measurement models, the present invention achieves rapid extraction of crack location information and accurate measurement of crack width.

[0093] See Figure 5 In an optional embodiment, to efficiently implement the crack width measurement method provided herein, the present invention further provides a crack width measurement system. The crack width measurement system comprises an interconnected input device, a processor, an output device, and a memory. The memory is configured to store a computer program comprising program instructions, and the processor is configured to invoke the program instructions to execute the specific steps of the crack width measurement method embodiments provided herein. The crack width measurement system of the present invention is structurally complete, objective, and stable, capable of efficiently implementing the crack width measurement method provided herein, thereby enhancing the overall applicability and practical application capabilities of the present invention.

[0094] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the above embodiments, or make equivalent replacements for some or all of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present invention, and they should all be included in the scope of the claims and description of the present invention.

Claims

1. A crack width measurement method, characterized in that: The steps include: Installing information monitoring equipment in the crack detection area and using the information monitoring equipment to obtain initial crack detection data; Constructing a detection data optimization model, and obtaining crack detection optimization data through the detection data optimization model; Establishing a detection data evaluation model, and obtaining crack detection target data based on the detection data evaluation model and the crack detection optimization data; extracting crack detection position information based on the crack detection target data; The width of the crack to be detected is measured according to the crack width analysis model and the crack detection position information.

2. The crack width measurement method according to claim 1, characterized in that: The step of installing an information monitoring device in the crack detection area and obtaining initial crack detection data using the information monitoring device includes: An information monitoring device is installed according to the crack detection area, and the information monitoring device includes a plurality of dynamic cameras.

3. The crack width measurement method according to claim 1, characterized in that: The constructing of the detection data optimization model and obtaining crack detection optimization data through the detection data optimization model include: Obtaining a pixel ratio of an image to be detected based on the initial crack detection data; Establishing a detection data optimization model based on the pixel ratio; The crack detection optimized data is obtained by utilizing the detection data optimization model.

4. The crack width measurement method according to claim 3, characterized in that: The detection data optimization model satisfies the following relationship: in, Represents the optimized image. represents the minimum output value of the converted image, Represents the grayscale pixel ratio value of the image to be detected, Indicates the maximum output value of the converted image.

5. The crack width measurement method according to claim 1, characterized in that: The establishing of the detection data evaluation model and obtaining crack detection target data based on the detection data evaluation model and the crack detection optimization data includes: constructing a detection data evaluation model using the crack detection optimization data; The data evaluation result of the image to be detected is obtained through the detection data evaluation model.

6. The crack width measurement method according to claim 5, characterized in that: The test data evaluation model satisfies the following relationship: in, represents the evaluation result of the image data set to be detected, Indicates the total number of images to be detected, Represents the initial data set of the image to be detected, represents the dataset of detection image references, represents the fluctuation coefficient of the data acquisition device, Indicates the external influence weight of the monitored object.

7. The crack width measurement method according to claim 1, characterized in that: The obtaining of crack detection target data based on the detection data evaluation model and the crack detection optimization data includes: Using the detection data evaluation model to evaluate and analyze the crack detection optimization data, and obtain data evaluation results; The crack detection target data is obtained by combining the data evaluation results and the detection data optimization model.

8. The crack width measurement method according to claim 1, characterized in that: Extracting crack detection position information based on the crack detection target data includes: Construct a crack location correction model; The crack position information to be detected is obtained based on the crack position correction model and the crack detection target data.

9. The crack width measurement method according to claim 1, characterized in that: The measuring of the width of the crack to be detected based on the crack width analysis model and the crack detection position information includes: Construct a crack width analysis model; The crack width analysis model satisfies the following relationship: in, Represents the distance between any two detection points in the image to be detected, Indicates the first dimension in the horizontal direction of the first detection point of the image to be detected, Represents the first dimension in the horizontal direction of the second detection point of the image to be detected, Represents the second dimension in the horizontal direction of the first detection point of the image to be detected, Indicates the second dimension in the horizontal direction of the second detection point of the image to be detected, Indicates the third dimension of the first detection point of the image to be detected perpendicular to the horizontal direction of the image, Indicates the third dimension of the second detection point of the image to be detected, which is perpendicular to the horizontal direction of the image.

10. A crack width measurement system, characterized in that: The system includes a processor, an input device, an output device and a memory, which are interconnected. The memory is used to store a computer program, and the computer program includes program instructions. The processor is configured to call the program instructions to execute the crack width measurement method according to any one of claims 1 to 9.

Images